INDEX

Explanations

the name 'Gordon' and variations of it in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

udder

-0.16

zah

-0.14

.appspot

-0.14

argon

-0.14

 ÐĶÐµÑĢÐ¶Ð°Ð²

-0.14

agus

-0.14

à¥Īà¤²

-0.14

ÙĦÙĬØ©

-0.13

ordova

-0.13

ìĥ

-0.13

POSITIVE LOGITS

uir

0.15

 âĸ³

0.15

 Charg

0.15

 Trojan

0.14

ÏĢÎ¹

0.14

imde

0.14

heed

0.14

 mixed

0.14

 hybrid

0.14

 retail

0.13

Activations Density 0.155%

the name 'Gordon' and variations of it in different contexts

No Comments

No Known Activations